SOTAVerified

Super-Resolution

Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

( Credit: MemNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 541–550 of 3874 papers

TitleStatusHype
Knowledge Distillation based Degradation Estimation for Blind Super-ResolutionCode1
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-ResolutionCode1
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image SynthesisCode1
Perception-Oriented Single Image Super-Resolution using Optimal Objective EstimationCode1
GAN Prior based Null-Space Learning for Consistent Super-ResolutionCode1
Guided Depth Super-Resolution by Deep Anisotropic DiffusionCode1
N-Gram in Swin Transformers for Efficient Lightweight Image Super-ResolutionCode1
Diffusion Model Based Posterior Sampling for Noisy Linear Inverse ProblemsCode1
Hard Exudate Segmentation Supplemented by Super-Resolution with Multi-scale Attention Fusion ModuleCode1
Conffusion: Confidence Intervals for Diffusion ModelsCode1
Show:102550
← PrevPage 55 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified